© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4398
    Prev
    Next
    INDEX
    Explanations

    references to online communication platforms, particularly in the context of anonymity and community interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Board '/b/' and 4chan mentions

    np_acts-logits-general · gemini-2.0-flash

    4chan /b/, specific forums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.69
     easily
    -0.64
     fácilmente
    -0.61
     clearly
    -0.56
    easily
    -0.55
     easier
    -0.54
    queryInterface
    -0.53
     easy
    -0.51
     facilmente
    -0.51
     ExecuteAsync
    -0.50
    POSITIVE LOGITS
    >>
    0.79
    发表于
    0.66
     >>
    0.64
    fag
    0.63
     fap
    0.63
    脚注の使い方
    0.63
    ::_('
    0.60
     propOrder
    0.60
     margiela
    0.58
     desu
    0.57
    Activations Density 0.086%

    No Known Activations